New Study Proposes Honest Fusion Evaluation for Cross-Domain Deepfake Detection
A new arXiv paper addresses cross-domain video deepfake detection using frozen foundation-model experts combined via calibrated score averaging and per-video routing, with leakage audits and tail robustness checks.
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-11-13 05:00 · arXiv cs.CV
Honest Fusion Evaluation for Cross-Domain Deepfake Detection: Leakage Audits and Tail Robustness